On Wednesday 17 April 2013 19:41:38 José Orlando Pereira wrote:
> I'm still trying to understand why.

After running it under strace, I see that upon free() we get a 
madvise(DONTNEED). Is it
possible that when kernel is copying data into that block, it might simply be 
mapping in
buffer pages, giving us zero copy for free?

-- 
Jose Orlando Pereira

Attachment: smime.p7s
Description: S/MIME cryptographic signature

_______________________________________________
discuss mailing list
[email protected]
http://lists.corosync.org/mailman/listinfo/discuss

Reply via email to